Harry Norman, managing director of OAL explains the logic behind APRIL Eye: the first artificial intelligence-based solution for label and date code verification.
A product recall due to incorrect labelling on food packages can have a devastating impact on a business, both financially and reputationally, and can result in vast quantities of waste. For food manufacturers, label and date code verification systems exist to ensure product recalls or withdrawals are avoided by checking the correct dates are printed on the correct packages.
These systems can take a variety of forms – from a human eye reading dates to an automated system – but all have been historically prone to error for a variety of reasons. OAL is laser-focused on innovation and dedicated to helping manufacturers overcome the difficulties associated with label and date code errors so the company set about exploring ways in which it could eliminate the product recall for good.
Label and date code verification began its journey with operators checking the date codes against a pre-generated sheet containing the date codes for that product run. However, asking humans to check date codes for hours at a time meant that distraction and tiredness set in, leading to errors. As technology developed, some retailers began to insist that suppliers installed either a ￼vision system or an automated label and date code verification system on the line. Both systems utilised cameras and printers in the checking of date codes, removing the existing problems of tiredness or distraction. However, humans were still able to intervene with the systems and cause errors – whether this was by adding an extra printer to speed up production but not connecting it to the system, or changing the print information for that run. A solution was needed that could provide an independent check and take decisions away from the operators.
This was certainly the thought process of a large retailer who approached its food manufacturing suppliers at the beginning of 2017 with a view to solving the waste problem that sits at the heart of food manufacturing.
Incorrect date codes and packaging are one of the largest sources of food waste; an estimated £60-£80 million problem, excluding the energy and environmental impact.
Two of the retailer’s suppliers, leading global food manufacturers, contacted OAL to ask them to work alongside them to develop a failsafe solution to combat the issue of incorrect date codes entering the supply chain. The solution would need to meet the retailer’s expectations, and in the process eliminate waste, product recalls and cut the manufacturers’ costs.
OAL undertook the project as part of its Food Manufacturing Digitalisation Strategy. The company had already been awarded an Innovate UK grant in 2017 and used part of the funds in their partnership with the University of Lincoln to investigate how artificial intelligence could revolutionise this fundamental area of the food manufacturing process. The University of Lincoln put together a team of global experts in AI, including Professor Stefanos Kollias, the founding professor of machine learning, and Professor Xujiong Ye, who led the Computational Vision research group at the university, to work alongside OAL to develop a solution.
Professor Kollias, who headed the team, had been brought to the University of Lincoln to spearhead the machine learning division of the faculty. He has produced world-leading research in the field of machine learning and is an IEEE Fellow (2015, suggested by the IEEE Computational Intelligence Society). The University attracted more talent from as far afield as Greece, Iceland and China, and the project began in November 2017.
We then delivered the solution.
Continue reading article…